Downloads · 30 days
53
27% of all-time downloads
Om22s/alexandria-qwen3-14b-rightsclean-speaker-attribution-attrv1
alexandria-qwen3-14b-rightsclean-speaker-attribution-attrv1 is a text generation model from Om22s. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
Training prompt: attrv1 — defaultpromptsattribute.txt at b02d5950; sha256 of the file e5fd22ad62af5bdc… (text: prompts/attrv1.txt in Om22s/alexandria-qwen3-attribution). Evidence: training manifest commit, clean tree.…
Downloads · 30 days
53
27% of all-time downloads
All-time downloads
199
Public
Repo size
385 MB
Likes
0
Public
Click a slice to open those files.
.safetensors257 MB · 67%
From the Hugging Face model README
Training prompt: attrv1 — default_prompts_attribute.txt at b02d5950; sha256 of the file e5fd22ad62af5bdc… (text: prompts/attrv1.txt in Om22s/alexandria-qwen3-attribution). Evidence: training manifest commit, clean tree. Repository renamed on 2026-09-27 to carry the label; the old URL redirects.
Training-data rights, stated plainly (2026-09-19). The novels are public domain, RiQuA's annotations are published for "use, modification, and experimentation", and the DraCor plays are CC0. The PDNC annotations (the speaker labels this adapter was trained on) come from a repository that states no licence; permission to train on and redistribute adapters from them has been requested from the corpus authors and this card will record their answer. No corpus text or annotation is redistributed here — weights and a hash manifest only.
Superseded. These weights are byte-identical to
adapters/qwen3-14b-rightscleanin the collection repo (safetensors sha256 4e516f8a…, GGUF c0dae304…). Current releases live inOm22s/alexandria-qwen3-attribution; this repo stays for reproducibility of the numbers below and is not updated.
An adapter-only PEFT/LoRA adapter for structured speaker attribution with
Qwen/Qwen3-14B. The base model is not included; download it separately.
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base_id = "Qwen/Qwen3-14B"
tokenizer = AutoTokenizer.from_pretrained(base_id)
base = AutoModelForCausalLM.from_pretrained(base_id, device_map="auto")
model = PeftModel.from_pretrained(
base, "Om22s/alexandria-qwen3-14b-rightsclean-speaker-attribution"
)
This adapter targets Alexandria's structured attribution prompt, not ordinary
chat. Require one JSON {"n","speaker"} object per input entry and reject
malformed or incomplete responses. The included rightsclean-attrv1.f16.gguf is a
runtime export for compatible llama.cpp workflows.
The exact prompt used for training and evaluation is included in
default_prompts_attribute.txt.
Four-book product-window evaluation (temperature 0, batch 25, 4096-token budget; 768 paired gold rows):
The result is an aggregate measurement from the in-repository evaluator. No source text, raw model responses, or copyrighted evaluation rows are included.
The training mixture was rights-reviewed and selected from sources with documented redistribution terms (PDNC, RiQuA, and DraCor prose). This release contains the adapter weights and recipe summary only; it does not redistribute the source datasets. Review each source's current license and the base model's terms before redistribution or commercial use.
LoRA recipe: rank 16, alpha 32, dropout 0.05, two epochs, learning rate 1e-4, maximum sequence length 2048, seed 20260914.
Performance is measured on the Alexandria four-book gold fixture and may not generalize to other genres, languages, prompts, or roster construction rules. The adapter does not provide speaker diarization, voice synthesis, or a general-purpose conversational model.
For: assigning a speaker name to each already-segmented line of an
English novel, given a roster, inside Alexandria Audiobook's structured
attribution prompt (default_prompts_attribute.txt).
Validate every reply: one {"n","speaker"} object per entry, every index
once, speakers from the roster plus NARRATOR/UNKNOWN.
Not for: chat, summarisation, translation, other languages (untested), texts without a roster, or decisions about real people. The adapter inherits the base model's limitations and does not change its safety behaviour.
Qwen/Qwen3-14B (bf16 ≈ 30 GB, or the Q4_K_M GGUF ≈ 9 GB); an r16 LoRA in safetensors plus an f16 GGUF export for llama-server --lora; 32k context, one slot. Loading with transformers/PEFT was written against transformers
4.57, peft 0.18, torch 2.10 (examples/infer.py); the scores were produced
with llama.cpp serving at temperature 0 (examples/serve_llamacpp.sh).
Adapter weights: Apache-2.0 (LICENSE). Base model: Qwen/Qwen3-14B,
Apache-2.0. v1.0.0 tags the state described here; main will not move.
Source and issues: on22s/alexandria-audiobook2.